Lightweight WaSR-T Network for Detection Boat Approaching a Tsunami Early Warning System
Keywords:
Marine Object RecognitionAbstract
A tsunami early warning system using buoys is vital for early warning of tsunami waves. Its vulnerability to tampering and even vandalism emphasizes the need for an object detection vision system for tsunami buoys. Moreover, researchers typically position these buoys at considerable distances from the seashore. The current tsunami early warning system lacks an object detection system capable of providing warnings about the presence of other disturbing objects. Hence, any system vision must incorporate object detection with energy efficiency. This research studies various efficient object detection network models that support object detection systems for these tsunami buoys. WaSR-T model network with temporal context was developed and equipped with a lightweight encoder MobileNetV3 to run on a single board computer. Experiments on a Jetson Nano revealed that lightweight WaSR-T using the MobileNetV3 encoder can detect ships in various sea conditions. Although the test results show less than optimal performance than the original network model, the experiments highlight that the lightweight WaSR-T remains the most promising for object monitoring on tsunami buoys, given its low memory requirements. Researchers can also implement it in other mid-ocean monitoring applications, such as rigs and marine platforms.
Downloads
References
L. Zhao, F. Yu, J. Hou, P. Wang, and T. Fan, “The role of tsunami buoy played in tsunami warning and its application in South China Sea,” Theor. Appl. Mech. Lett., vol. 3, no. 3, p. 032002, 2013, doi: 10.1063/2.1303202.
Y. Peng, Y. Qin, X. Tang, Z. Zhang, and L. Deng, “Survey on Image and Point-Cloud Fusion-Based Object Detection in Autonomous Vehicles,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 12, pp. 22772–22789, Dec. 2022, doi: 10.1109/TITS.2022.3206235.
L. Peng, H. Wang, and J. Li, “Uncertainty Evaluation of Object Detection Algorithms for Autonomous Vehicles,” Automot. Innov., vol. 4, no. 3, pp. 241–252, Aug. 2021, doi: 10.1007/s42154-021-00154-0.
N. GENGEÇ, O. EKER, H. ÇEVİKALP, A. YAZICI, and H. S. YAVUZ, “Visual object detection for autonomous transport vehicles in smart factories,” TURKISH J. Electr. Eng. Comput. Sci., vol. 29, no. 4, pp. 2101–2115, Jul. 2021, doi: 10.3906/elk-2008-62.
S. A. Khalil, S. Abdul-Rahman, S. Mutalib, and N. M. A. A. Dazlee, “Object Detection for Autonomous Vehicles with Sensor-based Technology Using YOLO,” Int. J. Intell. Syst. Appl. Eng., vol. 10, no. 1, pp. 129–134, Mar. 2022, doi: 10.18201/ijisae.2022.276.
B. Bovcon and M. Kristan, “WaSR—A Water Segmentation and Refinement Maritime Obstacle Detection Network,” IEEE Trans. Cybern., vol. 52, no. 12, pp. 12661–12674, Dec. 2022, doi: 10.1109/TCYB.2021.3085856.
L. Žust and M. Kristan, “Temporal Context for Robust Maritime Obstacle Detection,” Mar. 2022, [Online]. Available: http://arxiv.org/abs/2203.05352
M. Teršek, L. Žust, and M. Kristan, “eWaSR -- an embedded-compute-ready maritime obstacle detection network,” Apr. 2023, [Online]. Available: http://arxiv.org/abs/2304.11249
B. Bovcon, J. Muhovic, J. Pers, and M. Kristan, “The MaSTr1325 dataset for training deep USV obstacle detection models,” in 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Nov. 2019, pp. 3431–3438. doi: 10.1109/IROS40897.2019.8967909.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 770–778, Dec. 2016, doi: 10.1109/CVPR.2016.90.
A. Howard et al., “Searching for MobileNetV3,” May 2019, [Online]. Available: http://arxiv.org/abs/1905.02244
A. G. Howard et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” Apr. 2017, [Online]. Available: http://arxiv.org/abs/1704.04861
J. Hu, L. Shen, and G. Sun, “Squeeze-and-Excitation Networks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2018, pp. 7132–7141. doi: 10.1109/CVPR.2018.00745.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2018, pp. 4510–4520. doi: 10.1109/CVPR.2018.00474.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” Dec. 2015, [Online]. Available: http://arxiv.org/abs/1512.03385
B. Bovcon, J. Muhovič, D. Vranac, D. Mozetič, J. Perš, and M. Kristan, “MODS -- A USV-oriented object detection and obstacle segmentation benchmark,” May 2021, doi: 10.1109/TITS.2021.3124192.
Z. Chen and H. Zhu, “Visual Quality Evaluation for Semantic Segmentation: Subjective Assessment Database and Objective Assessment Measure,” IEEE Trans. Image Process., vol. 28, no. 12, pp. 5785–5796, Dec. 2019, doi: 10.1109/TIP.2019.2922072.
G. Csurka, D. Larlus, and F. Perronnin, “What is a good evaluation measure for semantic segmentation?,” in Procedings of the British Machine Vision Conference 2013, 2013, pp. 32.1-32.11. doi: 10.5244/C.27.32.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 ITB Graduate School Conference
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
